The clear magnetic resonance (MR) images play an important role in clinical medicine and diagnosis. However, its application in clinical diagnosis may be limited by the long acquisition and transformation time of MR images. To deal with this disadvantage, compressed sensing methods have been widely used in real reconstructing MR images. This paper presents an accurate and efficient compressed sensing model based on median filter for MR image reconstruction. By combining a total variation term, a median filter term which are presented in the L1 norm formulation and a data fitting term together, we propose a minimization problem for image reconstruction. The L1 norm formulation guarantees that the split Bregman method can be applied to efficiently minimize the energy functional in both the total variation term and the median filter term. We apply our model to lots of MR images to test its performance and compare it with a related method. Experimental results show the accuracy and efficiency of the proposed model.
Accurate medical image segmentation can greatly improve doctors’ speed of diagnosis and diagnosis rate. But the medical image is usually accompanied by the intensity inhomogeneity, which seriously interferes with the accuracy of segmentation results. In this paper, we propose a novel active contour model with the level set formulation to deal with this problem. With the bias field added into the energy functional, our model not only can accurately segment inhomogeneous images, but also can effectively eliminate the intensity inhomogeneity to get homogeneous correction images. Since our energy functional has a special form similar to the L1 regularization problem, we prefer to apply the split Bregman method to efficiently minimize the energy functional. Then, we use a variety of medical images to test the performance of our model. Experimental results demonstrate that our model can be applied in medical images with satisfactory results. Besides, qualitative and quantitative comparisons with the LSE model further demonstrate the superiority of our model in segmentation accuracy, correction effect and efficiency. The robustness to initial contour and noises is also verified to be the outstanding advantage of our model.
KEYWORDS: Image segmentation, Brain, Neuroimaging, Magnetic resonance imaging, Image processing, Sensors, Binary data, Data modeling, Mathematical modeling, Control systems
This paper presents a fast multiphase segmentation model for inhomogeneous images by incorporating the multiphase formulation of the local and global intensity fitting energy model and the split Bregman method. By applying the globally convex image segmentation idea, we first define a new energy functional, which is then modified by incorporating information from the edge. A weight function that varies dynamically with the location of the image is applied to balance the weights between the local and global intensity fitting terms. The split Bregman method is then applied to minimize our energy functional much more efficiently. Our model can segment more general images accurately, especially images with inhomogeneity. We have applied our model to synthetic and real inhomogeneous images with desirable results. Numerical results demonstrate that our model is superior to the piecewise constant multiphase models and the local binary fitting model. The results obtained by our model are even more accurate than the original local and global intensity fitting energy model.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.